Agent
Fresh-context PROJECT.md alignment classifier - classifies a proposed change and cites the governing clause (verdict-only agent).
Production-ready Claude Code 2.0 setup for autonomous development
Agent
Fresh-context PROJECT.md alignment classifier - classifies a proposed change and cites the governing clause (verdict-only agent).
Agent
Automation quality tester — evaluates whether autonomous-dev's hooks, pipeline, and enforcement are working correctly. Use proactively after /implement sessions to detect step skipping, specification gaming, and pipeline degradation.
Agent
Semantic documentation drift detector and CHANGELOG automation.
Agent
Implementation specialist - writes clean, tested code following existing patterns.
Agent
Generate well-structured GitHub issue descriptions with research integration and scope enforcement.
Agent
Agent "mobile-tester" from akaszubski/autonomous-dev, covering mission, hard gate: appium mcp availability check, hard gate: environment security (sandbox only), hard gate: screenshot data safety and hard gate: 60-second timeout per test case.
Agent
Adversarial plan reviewer - challenges assumptions, identifies gaps, enforces minimalism.
Agent
Architecture planning and design for complex features.
Agent
Research codebase patterns and similar implementations.
Agent
Research patterns and best practices for implementation.
Agent
Intent evolution and drift detector — analyzes session patterns to propose alignment updates.
Agent
Code quality gate - reviews code for patterns, testing, documentation compliance.
Agent
Security scanning and vulnerability detection - OWASP compliance checker.
Agent
Spec-blind behavioral tester - validates implementation against specs without seeing implementation details.
Agent
AST-based test coverage analysis - identifies untested code and coverage gaps.
Agent
Testing specialist using the Quality Diamond model — specification-driven tests from acceptance criteria down through contract tests, property-based invariants, and unit tests (invoked in --tdd-first mode).
Agent
E2E browser testing specialist - writes persistent test files using Playwright MCP tools.